Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4477 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.5340. Min Act: -0.0000

Data Index: 692410 (The Pile)

Max Activating Token Index: 362

Text #1

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.4118. Min Act: -0.0000

Data Index: 776618 (The Pile)

Max Activating Token Index: 457

Text #2

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.2312. Min Act: -0.0000

Data Index: 958701 (The Pile)

Max Activating Token Index: 189

Text #3

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.1447. Min Act: -0.0000

Data Index: 404986 (The Pile)

Max Activating Token Index: 130

Text #4

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.2098. Min Act: -0.0000

Data Index: 331400 (The Pile)

Max Activating Token Index: 801

Text #5

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.0753. Min Act: -0.0000

Data Index: 1547924 (The Pile)

Max Activating Token Index: 729

Text #6

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.1447. Min Act: -0.0000

Data Index: 1437915 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.0421. Min Act: -0.0000

Data Index: 666891 (The Pile)

Max Activating Token Index: 449

Text #8

Max Range: 1.5340. Min Range: -1.5340

Max Act: 1.0034. Min Act: -0.0000

Data Index: 958712 (The Pile)

Max Activating Token Index: 65

Text #9

Max Range: 1.5340. Min Range: -1.5340

Max Act: 0.9619. Min Act: -0.0000

Data Index: 1575595 (The Pile)

Max Activating Token Index: 518

Text #10

Max Range: 1.5340. Min Range: -1.5340

Max Act: 0.9163. Min Act: -0.0000

Data Index: 1884184 (The Pile)

Max Activating Token Index: 654

Text #11

Max Range: 1.5340. Min Range: -1.5340

Max Act: 0.9049. Min Act: -0.0000

Data Index: 89974 (The Pile)

Max Activating Token Index: 906

Text #12

Max Range: 1.5340. Min Range: -1.5340

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1562174 (The Pile)

Max Activating Token Index: 445

Text #13

Max Range: 1.5340. Min Range: -1.5340

Max Act: 0.9322. Min Act: -0.0000

Data Index: 738297 (The Pile)

Max Activating Token Index: 654

Text #14

Max Range: 1.5340. Min Range: -1.5340

Max Act: 0.9316. Min Act: -0.0000

Data Index: 201719 (The Pile)

Max Activating Token Index: 764

Text #15

Max Range: 1.5340. Min Range: -1.5340

Max Act: 0.8975. Min Act: -0.0000

Data Index: 82473 (The Pile)

Max Activating Token Index: 832

Text #16

Max Range: 1.5340. Min Range: -1.5340

Max Act: 0.8974. Min Act: -0.0000

Data Index: 1752395 (The Pile)

Max Activating Token Index: 1021

Text #17

Max Range: 1.5340. Min Range: -1.5340

Max Act: 0.9425. Min Act: -0.0000

Data Index: 1318625 (The Pile)

Max Activating Token Index: 95

Text #18

Max Range: 1.5340. Min Range: -1.5340

Max Act: 0.9089. Min Act: -0.0000

Data Index: 510403 (The Pile)

Max Activating Token Index: 471

Text #19

Max Range: 1.5340. Min Range: -1.5340

Max Act: 0.8666. Min Act: -0.0000

Data Index: 905080 (The Pile)

Max Activating Token Index: 758